Journal of Marine Science and Engineering,
Journal Year:
2023,
Volume and Issue:
12(1), P. 13 - 13
Published: Dec. 20, 2023
The
accurate
estimation
of
the
spatial
and
temporal
distribution
chlorophyll-a
(Chl-a)
concentrations
in
South
China
Sea
(SCS)
is
crucial
for
understanding
marine
ecosystem
dynamics
water
quality
assessment.
However,
challenge
missing
values
satellite-derived
Chl-a
data
has
hindered
obtaining
complete
spatiotemporal
information.
Traditional
methods
deriving
are
based
on
modeling
measured
sensor
situ
measurements.
Spatiotemporal
imputation
difficult
due
to
inaccessibility
Chl-a.
In
this
study,
we
introduce
an
innovative
approach
that
incorporates
ocean
dataset
utilizes
random
forest
algorithm
predicting
concentration
SCS.
method
combines
feature
pattern
main
influencing
factors,
it
introduces
data,
which
a
high
correlation
with
Chl-a,
as
input
through
engineering.
Also,
compared
Random
Forest
(RF)
other
Machine
Learning
(ML)
methods.
results
show
(1)
datasets
can
provide
important
support
by
capturing
impact
dynamical
processes
ecological
roles
Sea.
(2)
RF
superior
reconstruction
Sea,
better
model
performance
smaller
errors.
This
study
provides
valuable
insight
researchers
practitioners
choosing
suitable
machine
learning
SCS,
facilitating
region’s
ecosystems
supporting
effective
environmental
management.
Environmental Science & Technology,
Journal Year:
2024,
Volume and Issue:
58(35), P. 15607 - 15618
Published: March 4, 2024
Harmful
algal
blooms
(HABs)
pose
a
significant
ecological
threat
and
economic
detriment
to
freshwater
environments.
In
order
develop
an
intelligent
early
warning
system
for
HABs,
big
data
deep
learning
models
were
harnessed
in
this
study.
Data
collection
was
achieved
utilizing
the
vertical
aquatic
monitoring
(VAMS).
Subsequently,
analysis
stratification
of
layer
conducted
employing
"DeepDPM-Spectral
Clustering"
method.
This
approach
drastically
reduced
number
predictive
enhanced
adaptability
system.
The
Bloomformer-2
model
developed
conduct
both
single-step
multistep
predictions
Chl-a,
integrating
"
Alert
Level
Framework"
issued
by
World
Health
Organization
accomplish
HABs.
case
study
Taihu
Lake
revealed
that
during
winter
2018,
water
column
could
be
partitioned
into
four
clusters
(Groups
W1-W4),
while
summer
2019,
five
S1-S5).
Moreover,
subsequent
task,
exhibited
superiority
performance
across
all
2018
2019
(MAE:
0.175-0.394,
MSE:
0.042-0.305,
MAPE:
0.228-2.279
prediction;
MAE:
0.184-0.505,
0.101-0.378,
0.243-4.011
prediction).
prediction
3
days
indicated
Group
W1
I
alert
state
at
times.
Conversely,
S1
mainly
under
alert,
with
seven
specific
time
points
escalating
II
alert.
Furthermore,
end-to-end
architecture
system,
coupled
automation
its
various
processes,
minimized
human
intervention,
endowing
it
characteristics.
research
highlights
transformative
potential
artificial
intelligence
environmental
management
emphasizes
importance
interpretability
machine
applications.
Frontiers in Earth Science,
Journal Year:
2023,
Volume and Issue:
11
Published: Feb. 16, 2023
Utilization
and
exploitation
of
marine
resources
by
humans
have
contributed
to
the
growth
research.
As
technology
progresses,
artificial
intelligence
(AI)
approaches
are
progressively
being
applied
maritime
research,
complementing
traditional
forecasting
models
observation
techniques
some
degree.
This
article
takes
algorithmic
model
as
its
starting
point,
references
several
application
trials,
methodically
elaborates
on
emerging
research
trend
mixing
machine
learning
physical
modeling
concepts.
discusses
evolution
methodologies
for
building
ocean
observations,
remote
sensing
satellites,
smart
sensors,
intelligent
underwater
robots,
construction
big
data.
We
also
cover
method
identifying
internal
waves
(IW),
heatwaves,
El
Niño-Southern
Oscillation
(ENSO),
sea
ice
using
algorithms.
In
addition,
we
analyze
applications
in
prediction
components,
including
physics-driven
numerical
models,
model-driven
statistical
data-driven
deep
combined
with
models.
review
shows
routes
observation,
phenomena
identification,
elements
forecasting,
examples
forecasts
their
future
development
trends
from
angles
points
view,
categorizing
various
uses
sector.
Remote Sensing,
Journal Year:
2023,
Volume and Issue:
15(18), P. 4486 - 4486
Published: Sept. 12, 2023
Accurate
prediction
of
future
chlorophyll-a
(Chl-a)
concentrations
is
great
importance
for
effective
management
and
early
warning
marine
ecological
systems.
However,
previous
studies
primarily
focused
on
inversion
reconstruction,
while
methods
predicting
Chl-a
remain
limited.
To
address
this
issue,
we
adopted
four
deep
learning
approaches,
including
Convolutional
LSTM
Network
(ConvLSTM),
Neural
Network-Long
Short-Term
Memory
(CNN-LSTM),
Eidetic
3D
(E3D-LSTM),
Self-Attention
ConvLSTM
(SA-ConvLSTM)
models,
to
predict
over
the
Yellow
Sea
Bohai
(YBS)
in
China.
Furthermore,
14
environmental
variables
obtained
from
remote
sensing
data
Moderate-resolution
Imaging
Spectroradiometer
(MODIS)
ECMWF
Reanalysis
v5
(ERA5)
were
utilized
study
area.
The
results
showed
that
all
models
performed
satisfactorily
YBS,
with
SA-ConvLSTM
exhibiting
a
closer
approximation
true
values.
analyzed
impact
Module
(SAM)
results.
Compared
model,
model
integrated
SAM
module
better
captured
subtle
large-scale
variations
within
exhibited
highest
accuracy,
one-month
Pearson
correlation
coefficient
reached
0.887.
Our
provides
an
available
approach
anticipating
large
area
sea.
